Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    while limitations, conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    0.52
    اری
    0.52
    ق
    0.49
    이니
    0.47
     thì
    0.47
    oun
    0.46
    ता
    0.46
    تی
    0.46
    را
    0.46
    ادت
    0.46
    POSITIVE LOGITS
     containment
    0.44
    NeedConnect
    0.42
    SpriteCollision
    0.41
     candlest
    0.41
     सतत
    0.40
     לח
    0.40
     הספר
    0.40
    已經
    0.40
    已被
    0.40
    SXml
    0.39
    Act Density 0.000%

    No Known Activations